Examples of WeightedPhraseInfo

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
    FieldFragList ffl = new FieldFragList( fragCharSize );

    List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
    Iterator<WeightedPhraseInfo> ite = fieldPhraseList.phraseList.iterator();
    WeightedPhraseInfo phraseInfo = null;
    int startOffset = 0;
    boolean taken = false;
    while( true ){
      if( !taken ){
        if( !ite.hasNext() ) break;
        phraseInfo = ite.next();
      }
      taken = false;
      if( phraseInfo == null ) break;

      // if the phrase violates the border of previous fragment, discard it and try next phrase
      if( phraseInfo.getStartOffset() < startOffset ) continue;

      wpil.clear();
      wpil.add( phraseInfo );
      int st = phraseInfo.getStartOffset() - MARGIN < startOffset ?
          startOffset : phraseInfo.getStartOffset() - MARGIN;
      int en = st + fragCharSize;
      startOffset = en;

      while( true ){
        if( ite.hasNext() ){
          phraseInfo = ite.next();
          taken = true;
          if( phraseInfo == null ) break;
        }
        else
          break;
        if( phraseInfo.getEndOffset() <= en )
          wpil.add( phraseInfo );
        else
          break;
      }
      ffl.add( st, en, wpil );
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
    if( fragCharSize < minFragCharSize )
      throw new IllegalArgumentException( "fragCharSize(" + fragCharSize + ") is too small. It must be " + minFragCharSize + " or higher." );
   
    List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
    IteratorQueue<WeightedPhraseInfo> queue = new IteratorQueue<WeightedPhraseInfo>(fieldPhraseList.getPhraseList().iterator());
    WeightedPhraseInfo phraseInfo = null;
    int startOffset = 0;
    while((phraseInfo = queue.top()) != null){
      // if the phrase violates the border of previous fragment, discard it and try next phrase
      if( phraseInfo.getStartOffset() < startOffset )  {
        queue.removeTop();
        continue;
      }
     
      wpil.clear();
      final int currentPhraseStartOffset = phraseInfo.getStartOffset();
      int currentPhraseEndOffset = phraseInfo.getEndOffset();
      int spanStart = Math.max(currentPhraseStartOffset - margin, startOffset);
      int spanEnd = Math.max(currentPhraseEndOffset, spanStart + fragCharSize);
      if (acceptPhrase(queue.removeTop(),  currentPhraseEndOffset - currentPhraseStartOffset, fragCharSize)) {
        wpil.add(phraseInfo);
      }
      while((phraseInfo = queue.top()) != null) { // pull until we crossed the current spanEnd
        if (phraseInfo.getEndOffset() <= spanEnd) {
          currentPhraseEndOffset = phraseInfo.getEndOffset();
          if (acceptPhrase(queue.removeTop(),  currentPhraseEndOffset - currentPhraseStartOffset, fragCharSize)) {
            wpil.add(phraseInfo);
          }
        } else {
          break;
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

41
42
43
44
45
46
47
48
49
50
51
    FieldFragList ffl = new SimpleFieldFragList( fragCharSize );

    List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
    Iterator<WeightedPhraseInfo> ite = fieldPhraseList.phraseList.iterator();
    WeightedPhraseInfo phraseInfo = null;
    while( true ){
      if( !ite.hasNext() ) break;
      phraseInfo = ite.next();
      if( phraseInfo == null ) break;
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
      assertEquals( "a(1.0)((0,1))", fpl.phraseList.get( 0 ).toString() );     
  }
  */

  public void testWeightedPhraseInfoComparisonConsistency() {
    WeightedPhraseInfo a = newInfo( 0, 0, 1 );
    WeightedPhraseInfo b = newInfo( 1, 2, 1 );
    WeightedPhraseInfo c = newInfo( 2, 3, 1 );
    WeightedPhraseInfo d = newInfo( 0, 0, 1 );
    WeightedPhraseInfo e = newInfo( 0, 0, 2 );

    assertConsistentEquals( a, a );
    assertConsistentEquals( b, b );
    assertConsistentEquals( c, c );
    assertConsistentEquals( d, d );
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

268
269
270
271
272
273
274
  }

  private WeightedPhraseInfo newInfo( int startOffset, int endOffset, float boost ) {
    LinkedList< TermInfo > infos = new LinkedList< TermInfo >();
    infos.add( new TermInfo( _TestUtil.randomUnicodeString( random() ), startOffset, endOffset, 0, 0 ) );
    return new WeightedPhraseInfo( infos, boost );
  }
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    FieldFragList ffl = new FieldFragList( fragCharSize );

    List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
    Iterator<WeightedPhraseInfo> ite = fieldPhraseList.phraseList.iterator();
    WeightedPhraseInfo phraseInfo = null;
    int startOffset = 0;
    boolean taken = false;
    while( true ){
      if( !taken ){
        if( !ite.hasNext() ) break;
        phraseInfo = ite.next();
      }
      taken = false;
      if( phraseInfo == null ) break;

      // if the phrase violates the border of previous fragment, discard it and try next phrase
      if( phraseInfo.getStartOffset() < startOffset ) continue;

      wpil.clear();
      wpil.add( phraseInfo );
      int st = phraseInfo.getStartOffset() - margin < startOffset ?
          startOffset : phraseInfo.getStartOffset() - margin;
      int en = st + fragCharSize;
      if( phraseInfo.getEndOffset() > en )
        en = phraseInfo.getEndOffset();
      startOffset = en;

      while( true ){
        if( ite.hasNext() ){
          phraseInfo = ite.next();
          taken = true;
          if( phraseInfo == null ) break;
        }
        else
          break;
        if( phraseInfo.getEndOffset() <= en )
          wpil.add( phraseInfo );
        else
          break;
      }
      ffl.add( st, en, wpil );
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
    if( fragCharSize < minFragCharSize )
      throw new IllegalArgumentException( "fragCharSize(" + fragCharSize + ") is too small. It must be " + minFragCharSize + " or higher." );
   
    List<WeightedPhraseInfo> wpil = new ArrayList<WeightedPhraseInfo>();
    Iterator<WeightedPhraseInfo> ite = fieldPhraseList.getPhraseList().iterator();
    WeightedPhraseInfo phraseInfo = null;
    int startOffset = 0;
    boolean taken = false;
    while( true ){
      if( !taken ){
        if( !ite.hasNext() ) break;
        phraseInfo = ite.next();
      }
      taken = false;
      if( phraseInfo == null ) break;

      // if the phrase violates the border of previous fragment, discard it and try next phrase
      if( phraseInfo.getStartOffset() < startOffset ) continue;

      wpil.clear();
      wpil.add( phraseInfo );
      int firstOffset = phraseInfo.getStartOffset();
      int st = phraseInfo.getStartOffset() - margin < startOffset ?
          startOffset : phraseInfo.getStartOffset() - margin;
      int en = st + fragCharSize;
      if( phraseInfo.getEndOffset() > en )
        en = phraseInfo.getEndOffset();

      int lastEndOffset = phraseInfo.getEndOffset();
      while( true ){
        if( ite.hasNext() ){
          phraseInfo = ite.next();
          taken = true;
          if( phraseInfo == null ) break;
        }
        else
          break;
        if( phraseInfo.getEndOffset() <= en ){
          wpil.add( phraseInfo );
          lastEndOffset = phraseInfo.getEndOffset();
        }
        else
          break;
      }
      int matchLen = lastEndOffset - firstOffset;
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
      assertEquals( "a(1.0)((0,1))", fpl.phraseList.get( 0 ).toString() );     
  }
  */

  public void testWeightedPhraseInfoComparisonConsistency() {
    WeightedPhraseInfo a = newInfo( 0, 0, 1 );
    WeightedPhraseInfo b = newInfo( 1, 2, 1 );
    WeightedPhraseInfo c = newInfo( 2, 3, 1 );
    WeightedPhraseInfo d = newInfo( 0, 0, 1 );
    WeightedPhraseInfo e = newInfo( 0, 0, 2 );

    assertConsistentEquals( a, a );
    assertConsistentEquals( b, b );
    assertConsistentEquals( c, c );
    assertConsistentEquals( d, d );
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

269
270
271
272
273
274
275
  }

  private WeightedPhraseInfo newInfo( int startOffset, int endOffset, float boost ) {
    LinkedList< TermInfo > infos = new LinkedList<>();
    infos.add( new TermInfo( TestUtil.randomUnicodeString(random()), startOffset, endOffset, 0, 0 ) );
    return new WeightedPhraseInfo( infos, boost );
  }
View Full Code Here

Examples of org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
    if( fragCharSize < minFragCharSize )
      throw new IllegalArgumentException( "fragCharSize(" + fragCharSize + ") is too small. It must be " + minFragCharSize + " or higher." );
   
    List<WeightedPhraseInfo> wpil = new ArrayList<>();
    IteratorQueue<WeightedPhraseInfo> queue = new IteratorQueue<>(fieldPhraseList.getPhraseList().iterator());
    WeightedPhraseInfo phraseInfo = null;
    int startOffset = 0;
    while((phraseInfo = queue.top()) != null){
      // if the phrase violates the border of previous fragment, discard it and try next phrase
      if( phraseInfo.getStartOffset() < startOffset )  {
        queue.removeTop();
        continue;
      }
     
      wpil.clear();
      final int currentPhraseStartOffset = phraseInfo.getStartOffset();
      int currentPhraseEndOffset = phraseInfo.getEndOffset();
      int spanStart = Math.max(currentPhraseStartOffset - margin, startOffset);
      int spanEnd = Math.max(currentPhraseEndOffset, spanStart + fragCharSize);
      if (acceptPhrase(queue.removeTop(),  currentPhraseEndOffset - currentPhraseStartOffset, fragCharSize)) {
        wpil.add(phraseInfo);
      }
      while((phraseInfo = queue.top()) != null) { // pull until we crossed the current spanEnd
        if (phraseInfo.getEndOffset() <= spanEnd) {
          currentPhraseEndOffset = phraseInfo.getEndOffset();
          if (acceptPhrase(queue.removeTop(),  currentPhraseEndOffset - currentPhraseStartOffset, fragCharSize)) {
            wpil.add(phraseInfo);
          }
        } else {
          break;
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.